© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 54274
    Prev
    Next
    INDEX
    Explanations

    dimensions related to diameter

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.47
     fédé
    -0.46
     arché
    -0.45
     Aplica
    -0.42
    Conf
    -0.42
     Acción
    -0.42
    本
    -0.41
     âme
    -0.41
    armée
    -0.41
    holding
    -0.40
    POSITIVE LOGITS
     diameter
    1.20
     Diameter
    1.18
    Diameter
    1.02
    diameter
    1.01
     Durchmesser
    0.99
     diameters
    0.95
     DIAM
    0.87
    直径
    0.81
     diámetro
    0.79
     diame
    0.73
    Activations Density 0.012%

    No Known Activations